Commit
•
f4adfc2
1
Parent(s):
3b7d3a9
Update README.md
Browse files
README.md
CHANGED
|
@@ -12,13 +12,12 @@ license: apache-2.0
|
|
| 12 |
|
| 13 |
Without any labeled downstream pairs for training, ZeroNLG is an unified framework that deals with multiple natural language generation (NLG) tasks in a zero-shot manner, including image-to-text, video-to-text, and text-to-text generation tasks across English, Chinese, German, and French.
|
| 14 |
|
| 15 |
-
Pre-trained data: a machine-translated version of [CC3M](https://huggingface.co/datasets/conceptual_captions), including
|
| 16 |
- 1.1M English sentences
|
| 17 |
- 1.1M English-Chinese pairs
|
| 18 |
- 1.1M English-German pairs
|
| 19 |
- 1.1M English-French pairs
|
| 20 |
|
| 21 |
-
|
| 22 |
Paper: [ZeroNLG: Aligning and Autoencoding Domains for Zero-Shot Multimodal and Multilingual Natural Language Generation](https://arxiv.org/abs/2303.06458)
|
| 23 |
|
| 24 |
Authors: *Bang Yang\*, Fenglin Liu\*, Yuexian Zou, Xian Wu, Yaowei Wang, David A. Clifton*
|
|
|
|
| 12 |
|
| 13 |
Without any labeled downstream pairs for training, ZeroNLG is an unified framework that deals with multiple natural language generation (NLG) tasks in a zero-shot manner, including image-to-text, video-to-text, and text-to-text generation tasks across English, Chinese, German, and French.
|
| 14 |
|
| 15 |
+
[Pre-trained data](https://drive.google.com/file/d/1yCLpDLDO5TnoqfyHKwgi51Fw66QliOvM/view?usp=share_link): a machine-translated version of [CC3M](https://huggingface.co/datasets/conceptual_captions), including
|
| 16 |
- 1.1M English sentences
|
| 17 |
- 1.1M English-Chinese pairs
|
| 18 |
- 1.1M English-German pairs
|
| 19 |
- 1.1M English-French pairs
|
| 20 |
|
|
|
|
| 21 |
Paper: [ZeroNLG: Aligning and Autoencoding Domains for Zero-Shot Multimodal and Multilingual Natural Language Generation](https://arxiv.org/abs/2303.06458)
|
| 22 |
|
| 23 |
Authors: *Bang Yang\*, Fenglin Liu\*, Yuexian Zou, Xian Wu, Yaowei Wang, David A. Clifton*
|